Triple
T9342888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dolores Park |
E224804
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | 20th Street |
E587054
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 20th Street | Statement: [Dolores Park, near, 20th Street]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 20th Street Context triple: [Dolores Park, near, 20th Street]
-
A.
20th Street
20th Street is an east–west thoroughfare in Manhattan, New York City, running through neighborhoods including the Flatiron District.
-
B.
North 20th Street
North 20th Street is a north–south thoroughfare in Philadelphia, Pennsylvania, running through Center City and several adjacent neighborhoods.
-
C.
25th Street
25th Street is a local New York City Subway station in Brooklyn serving the BMT Fourth Avenue Line.
-
D.
24th Street
chosen
24th Street is a major east–west thoroughfare in San Francisco known for its vibrant Latino culture, local businesses, and community life in the Mission District.
-
E.
28th Street
28th Street is a major commercial and transportation corridor running through Kentwood, Michigan and the greater Grand Rapids area.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca842993248190a79ab06968994b86 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4bb11cd08190b159a6066dd0ebf1 |
completed | April 1, 2026, 4:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0e4043e288190b05511d537b1614d |
completed | April 4, 2026, 10:12 a.m. |
Created at: March 30, 2026, 7:40 p.m.